Integrating Automated Electrochemistry and High‐Throughput Characterization with Machine Learning to Explore Si─Ge─Sn Thin‐Film Lithium Battery Anodes

A closed-loop, data-driven approach facilitates the exploration of high-performance Si─Ge─Sn alloys as promising fast-charging battery anodes. Autonomous electrochemical experimentation using a scanning droplet cell is combined with real-time optimization to efficiently navigate composition space. The lead material is upscaled to coin cells for long-term performance evaluation. Explainable machine learning unravels key composition–structure–property relationships through high-throughput Raman and XRD analysis.

Abstract

High-performance batteries need accelerated discovery and optimization of new anode materials. Herein, we explore the Si─Ge─Sn ternary alloy system as a candidate fast-charging anode materials system by utilizing a scanning droplet cell (SDC) as an autonomous electrochemical characterization tool with the goal of subsequent upscaling. As the SDC is performing experiments sequentially, an exploration of the entire ternary space is unfeasible due to time constraints. Thus, closed-loop optimization, guided by real-time data analysis and sequential learning algorithms, is utilized to direct experiments. The lead material identified is scaled up to a coin cell to validate the findings from the autonomous millimeter-scale thin-film electrochemical experimentation. Explainable machine learning (ML) models incorporating data from high-throughput Raman spectroscopy and X-ray diffraction (XRD) are used to elucidate the effect of short and long-range ordering on material performance.